Related papers: Evaluating Privilege Usage of Agents with Real-Wor…

Financial agents powered by large language models (LLMs) are increasingly deployed for investment analysis, risk assessment, and automated decision-making, where their abilities to plan, invoke tools, and manipulate mutable state introduce…

As LLMs become more common, non-expert users can pose risks, prompting extensive research into jailbreak attacks. However, most existing black-box jailbreak attacks rely on hand-crafted heuristics or narrow search spaces, which limit…

LLM agents operating in open environments face escalating risks from indirect prompt injection, particularly within the tool stream where manipulated metadata and runtime feedback hijack execution flow. Existing defenses encounter a…

Large Language Models (LLMs) have the potential to significantly enhance threat intelligence by automating the collection, preprocessing, and analysis of threat data. However, the usability of these tools is critical to ensure their…

Large Language Model (LLM) Agents are an emerging computing paradigm that blends generative machine learning with tools such as code interpreters, web browsing, email, and more generally, external resources. These agent-based systems…

The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, where an adversary induces an agent to execute dangerous…

Recent advances in Large Language Models (LLMs) have sparked concerns over their potential to acquire and misuse dangerous or high-risk capabilities, posing frontier risks. Current safety evaluations primarily test for what a model…

Graphical user interface (GUI) agents powered by multimodal large language models (MLLMs) have shown greater promise for human-interaction. However, due to the high fine-tuning cost, users often rely on open-source GUI agents or APIs…

System prompts are critical for guiding the behavior of Large Language Models (LLMs), yet they often contain proprietary logic or sensitive information, making them a prime target for extraction attacks. Adversarial queries can successfully…

Fine-tuning is a common and effective method for tailoring large language models (LLMs) to specialized tasks and applications. In this paper, we study the privacy implications of fine-tuning LLMs on user data. To this end, we consider a…

We introduce MPLSandbox, an out-of-the-box multi-programming language sandbox designed to provide unified and comprehensive feedback from compiler and analysis tools for Large Language Models (LLMs). It can automatically identify the…

Large language models (LLMs) are increasingly deployed as tool-using agents, shifting safety concerns from harmful text generation to harmful task completion. Deployed systems often condition on user profiles or persistent memory, yet agent…

LLM-based multi-agent systems (MAS) demonstrate increasing integration into next-generation applications, but their safety in backdoor attacks remains largely underexplored. However, existing research has focused exclusively on single-agent…

Recent research on reinforcement learning (RL) has suggested that trained agents are vulnerable to maliciously crafted adversarial samples. In this work, we show how such samples can be generalised from White-box and Grey-box attacks to a…

Finetuning pretrained large language models (LLMs) has become the standard paradigm for developing downstream applications. However, its security implications remain unclear, particularly regarding whether finetuned LLMs inherit jailbreak…

LLM agents require personal information for personalization in order to effectively act on users' behalf, but this raises privacy concerns that can discourage data sharing, limiting both the autonomy levels at which agents can operate and…

Large language models (LLMs) are increasingly deployed in a wide range of applications, yet remain vulnerable to adversarial jailbreak attacks that circumvent their safety guardrails. Existing evaluation frameworks typically report binary…

The rise of tool-using Large Language Model (LLM) agents, standardized by protocols like the Model Context Protocol (MCP), has unlocked unprecedented autonomous execution capabilities for LLM Agents by integrating external open-domain…

LLM agents have begun to appear as personal assistants, customer service bots, and clinical aides. While these applications deliver substantial operational benefits, they also require continuous access to sensitive data, which increases the…

LLM-based multi-agent systems (MASs) are transforming personal productivity by autonomously executing complex, cross-platform tasks. Frameworks such as OpenClaw demonstrate the potential of locally deployed agents integrated with personal…